9. Multiple Comparison Tests and Confidence Intervals

  1. Bradley E. Huitema

Published Online: 14 OCT 2011

DOI: 10.1002/9781118067475.ch9

The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition

The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition

How to Cite

Huitema, B. E. (2011) Multiple Comparison Tests and Confidence Intervals, in The Analysis of Covariance and Alternatives: Statistical Methods for Experiments, Quasi-Experiments, and Single-Case Studies, Second Edition, John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9781118067475.ch9

Author Information

  1. Department of Psychology, Western Michigan University, Kalamazoo, Michigan, USA

Publication History

  1. Published Online: 14 OCT 2011
  2. Published Print: 14 OCT 2011

Book Series:

  1. Wiley Series in Probability and Statistics

Book Series Editors:

  1. Walter A. Shewhart and
  2. Samuel S. Wilks

ISBN Information

Print ISBN: 9780471748960

Online ISBN: 9781118067475

SEARCH

Keywords:

  • Bonferroni procedure;
  • confidence intervals;
  • Fisher–Hayter test;
  • multiple comparison procedures;
  • Scheffé procedure;
  • Tukey–Kramer method

Summary

This chapter presents the multiple comparison methods along with two additional methods. It discusses the four multiple comparison procedures. They include the following methods: (1) Fisher–Hayter (F–H), (2) Tukey–Kramer (T–K), (3) Bonferroni, and (4) Scheffé. The choice among these procedures should be based on the type of comparisons of greatest interest to the investigator and whether simultaneous confidence intervals are desired. The most frequently encountered multiple comparison situation is the one in which the researcher is interested in all pairwise comparisons. Many multiple comparison tests can be used in this situation but the Fisher–Hayter test generally has higher power than the popular competing procedures. The Tukey–Kramer method is appropriate for all pairwise tests and/or simultaneous confidence intervals. The Scheffé procedure is the most general of the available procedures for making multiple comparisons. The correct interpretation of multiple comparison procedures is based on the concept of familywise error.

Controlled Vocabulary Terms

Holm’s Bonferroni method; multiple comparison problem; Tukey range test